1. Patchew
  2. linux
  3. [PATCH v2 0/5] KVM: x86/pmu: Add support for AMD Host-Only/Guest-Only bits
  4. View patch

[PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions

Jim Mattson posted 5 patches 1 week, 2 days ago
There is a newer version of this series
[PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions
Posted by Jim Mattson 1 week, 2 days ago 
Add amd_pmu_refresh_host_guest_eventsel_hw() to recalculate eventsel_hw for
all PMCs based on the current vCPU state. This is needed because Host-Only
and Guest-Only counters must be enabled/disabled at:

  - SVME changes: When EFER.SVME is modified, counters with Guest-Only bits
    need their hardware enable state updated.

  - Nested transitions: When entering or leaving guest mode, Host-Only
    counters should be disabled/enabled and Guest-Only counters should be
    enabled/disabled accordingly.

Introduce svm_enter_guest_mode() and svm_leave_guest_mode() wrappers that
call enter_guest_mode()/leave_guest_mode() followed by the PMU refresh,
ensuring the PMU state stays synchronized with guest mode transitions.

Signed-off-by: Jim Mattson <jmattson@google.com>
---
 arch/x86/kvm/svm/nested.c |  6 +++---
 arch/x86/kvm/svm/pmu.c    | 12 ++++++++++++
 arch/x86/kvm/svm/svm.c    |  2 ++
 arch/x86/kvm/svm/svm.h    | 17 +++++++++++++++++
 4 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index de90b104a0dd..a7d1901f256b 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -757,7 +757,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	nested_svm_transition_tlb_flush(vcpu);
 
 	/* Enter Guest-Mode */
-	enter_guest_mode(vcpu);
+	svm_enter_guest_mode(vcpu);
 
 	/*
 	 * Filled at exit: exit_code, exit_info_1, exit_info_2, exit_int_info,
@@ -1136,7 +1136,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	vmcb12 = map.hva;
 
 	/* Exit Guest-Mode */
-	leave_guest_mode(vcpu);
+	svm_leave_guest_mode(vcpu);
 	svm->nested.vmcb12_gpa = 0;
 	WARN_ON_ONCE(svm->nested.nested_run_pending);
 
@@ -1402,7 +1402,7 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
 		svm->nested.nested_run_pending = 0;
 		svm->nested.vmcb12_gpa = INVALID_GPA;
 
-		leave_guest_mode(vcpu);
+		svm_leave_guest_mode(vcpu);
 
 		svm_switch_vmcb(svm, &svm->vmcb01);
 
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 8d451110a94d..e2a849fc7daa 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -171,6 +171,18 @@ static void amd_pmu_set_eventsel_hw(struct kvm_pmc *pmc)
 	pmc->eventsel_hw &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 }
 
+void amd_pmu_refresh_host_guest_eventsel_hw(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int i;
+
+	if (pmu->reserved_bits & AMD64_EVENTSEL_HOST_GUEST_MASK)
+		return;
+
+	for (i = 0; i < pmu->nr_arch_gp_counters; i++)
+		amd_pmu_set_eventsel_hw(&pmu->gp_counters[i]);
+}
+
 static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5f0136dbdde6..498e098a3df0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -244,6 +244,8 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 			if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm))
 				set_exception_intercept(svm, GP_VECTOR);
 		}
+
+		amd_pmu_refresh_host_guest_eventsel_hw(vcpu);
 	}
 
 	svm->vmcb->save.efer = efer | EFER_SVME;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index ebd7b36b1ceb..86d4d37bfb08 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -864,6 +864,23 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa);
 void sev_es_unmap_ghcb(struct vcpu_svm *svm);
 
+
+/* pmu.c */
+void amd_pmu_refresh_host_guest_eventsel_hw(struct kvm_vcpu *vcpu);
+
+
+static inline void svm_enter_guest_mode(struct kvm_vcpu *vcpu)
+{
+	enter_guest_mode(vcpu);
+	amd_pmu_refresh_host_guest_eventsel_hw(vcpu);
+}
+
+static inline void svm_leave_guest_mode(struct kvm_vcpu *vcpu)
+{
+	leave_guest_mode(vcpu);
+	amd_pmu_refresh_host_guest_eventsel_hw(vcpu);
+}
+
 #ifdef CONFIG_KVM_AMD_SEV
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp);
 int sev_mem_enc_register_region(struct kvm *kvm,
-- 
2.53.0.rc1.225.gd81095ad13-goog
Re: [PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions
Posted by Yosry Ahmed 1 week, 2 days ago 
On Thu, Jan 29, 2026 at 03:28:08PM -0800, Jim Mattson wrote:
> Add amd_pmu_refresh_host_guest_eventsel_hw() to recalculate eventsel_hw for
> all PMCs based on the current vCPU state. This is needed because Host-Only
> and Guest-Only counters must be enabled/disabled at:
> 
>   - SVME changes: When EFER.SVME is modified, counters with Guest-Only bits
>     need their hardware enable state updated.
> 
>   - Nested transitions: When entering or leaving guest mode, Host-Only
>     counters should be disabled/enabled and Guest-Only counters should be
>     enabled/disabled accordingly.
> 
> Introduce svm_enter_guest_mode() and svm_leave_guest_mode() wrappers that
> call enter_guest_mode()/leave_guest_mode() followed by the PMU refresh,
> ensuring the PMU state stays synchronized with guest mode transitions.
> 
> Signed-off-by: Jim Mattson <jmattson@google.com>
> ---
>  arch/x86/kvm/svm/nested.c |  6 +++---
>  arch/x86/kvm/svm/pmu.c    | 12 ++++++++++++
>  arch/x86/kvm/svm/svm.c    |  2 ++
>  arch/x86/kvm/svm/svm.h    | 17 +++++++++++++++++
>  4 files changed, 34 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> index de90b104a0dd..a7d1901f256b 100644
> --- a/arch/x86/kvm/svm/nested.c
> +++ b/arch/x86/kvm/svm/nested.c
> @@ -757,7 +757,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
>  	nested_svm_transition_tlb_flush(vcpu);
>  
>  	/* Enter Guest-Mode */
> -	enter_guest_mode(vcpu);
> +	svm_enter_guest_mode(vcpu);

FWIW, I think this name is a bit confusing because we also have
enter_svm_guest_mode(). So we end up with:

enter_svm_guest_mode() -> nested_vmcb02_prepare_control() ->
svm_enter_guest_mode() -> enter_guest_mode()

I actually have another proposed change [1] that moves
enter_guest_mode() directly into enter_svm_guest_mode(), so the sequence
would end up being:

enter_svm_guest_mode() -> svm_enter_guest_mode() -> enter_guest_mode()

[1] https://lore.kernel.org/kvm/20260115011312.3675857-9-yosry.ahmed@linux.dev/
Re: [PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions
Posted by Jim Mattson 1 week, 1 day ago 
On Fri, Jan 30, 2026 at 7:26 AM Yosry Ahmed <yosry.ahmed@linux.dev> wrote:
>
> On Thu, Jan 29, 2026 at 03:28:08PM -0800, Jim Mattson wrote:
> > Add amd_pmu_refresh_host_guest_eventsel_hw() to recalculate eventsel_hw for
> > all PMCs based on the current vCPU state. This is needed because Host-Only
> > and Guest-Only counters must be enabled/disabled at:
> >
> >   - SVME changes: When EFER.SVME is modified, counters with Guest-Only bits
> >     need their hardware enable state updated.
> >
> >   - Nested transitions: When entering or leaving guest mode, Host-Only
> >     counters should be disabled/enabled and Guest-Only counters should be
> >     enabled/disabled accordingly.
> >
> > Introduce svm_enter_guest_mode() and svm_leave_guest_mode() wrappers that
> > call enter_guest_mode()/leave_guest_mode() followed by the PMU refresh,
> > ensuring the PMU state stays synchronized with guest mode transitions.
> >
> > Signed-off-by: Jim Mattson <jmattson@google.com>
> > ---
> >  arch/x86/kvm/svm/nested.c |  6 +++---
> >  arch/x86/kvm/svm/pmu.c    | 12 ++++++++++++
> >  arch/x86/kvm/svm/svm.c    |  2 ++
> >  arch/x86/kvm/svm/svm.h    | 17 +++++++++++++++++
> >  4 files changed, 34 insertions(+), 3 deletions(-)
> >
> > diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> > index de90b104a0dd..a7d1901f256b 100644
> > --- a/arch/x86/kvm/svm/nested.c
> > +++ b/arch/x86/kvm/svm/nested.c
> > @@ -757,7 +757,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
> >       nested_svm_transition_tlb_flush(vcpu);
> >
> >       /* Enter Guest-Mode */
> > -     enter_guest_mode(vcpu);
> > +     svm_enter_guest_mode(vcpu);
>
> FWIW, I think this name is a bit confusing because we also have
> enter_svm_guest_mode(). So we end up with:
>
> enter_svm_guest_mode() -> nested_vmcb02_prepare_control() ->
> svm_enter_guest_mode() -> enter_guest_mode()
>
> I actually have another proposed change [1] that moves
> enter_guest_mode() directly into enter_svm_guest_mode(), so the sequence
> would end up being:
>
> enter_svm_guest_mode() -> svm_enter_guest_mode() -> enter_guest_mode()

Yes, that is confusing. What if I renamed the existing function to
something like svm_nested_switch_to_vmcb02()?

Alternatively, I could go back to introducing a new PMU_OP, call it
from {enter,leave}_guest_mode(), and drop the wrappers.

> [1] https://lore.kernel.org/kvm/20260115011312.3675857-9-yosry.ahmed@linux.dev/
Re: [PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions
Posted by Yosry Ahmed 1 week, 1 day ago 
January 30, 2026 at 3:30 PM, "Jim Mattson" <jmattson@google.com> wrote:


> 
> On Fri, Jan 30, 2026 at 7:26 AM Yosry Ahmed <yosry.ahmed@linux.dev> wrote:
> 
> > 
> > On Thu, Jan 29, 2026 at 03:28:08PM -0800, Jim Mattson wrote:
> >  Add amd_pmu_refresh_host_guest_eventsel_hw() to recalculate eventsel_hw for
> >  all PMCs based on the current vCPU state. This is needed because Host-Only
> >  and Guest-Only counters must be enabled/disabled at:
> > 
> >  - SVME changes: When EFER.SVME is modified, counters with Guest-Only bits
> >  need their hardware enable state updated.
> > 
> >  - Nested transitions: When entering or leaving guest mode, Host-Only
> >  counters should be disabled/enabled and Guest-Only counters should be
> >  enabled/disabled accordingly.
> > 
> >  Introduce svm_enter_guest_mode() and svm_leave_guest_mode() wrappers that
> >  call enter_guest_mode()/leave_guest_mode() followed by the PMU refresh,
> >  ensuring the PMU state stays synchronized with guest mode transitions.
> > 
> >  Signed-off-by: Jim Mattson <jmattson@google.com>
> >  ---
> >  arch/x86/kvm/svm/nested.c | 6 +++---
> >  arch/x86/kvm/svm/pmu.c | 12 ++++++++++++
> >  arch/x86/kvm/svm/svm.c | 2 ++
> >  arch/x86/kvm/svm/svm.h | 17 +++++++++++++++++
> >  4 files changed, 34 insertions(+), 3 deletions(-)
> > 
> >  diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> >  index de90b104a0dd..a7d1901f256b 100644
> >  --- a/arch/x86/kvm/svm/nested.c
> >  +++ b/arch/x86/kvm/svm/nested.c
> >  @@ -757,7 +757,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
> >  nested_svm_transition_tlb_flush(vcpu);
> > 
> >  /* Enter Guest-Mode */
> >  - enter_guest_mode(vcpu);
> >  + svm_enter_guest_mode(vcpu);
> > 
> >  FWIW, I think this name is a bit confusing because we also have
> >  enter_svm_guest_mode(). So we end up with:
> > 
> >  enter_svm_guest_mode() -> nested_vmcb02_prepare_control() ->
> >  svm_enter_guest_mode() -> enter_guest_mode()
> > 
> >  I actually have another proposed change [1] that moves
> >  enter_guest_mode() directly into enter_svm_guest_mode(), so the sequence
> >  would end up being:
> > 
> >  enter_svm_guest_mode() -> svm_enter_guest_mode() -> enter_guest_mode()
> > 
> Yes, that is confusing. What if I renamed the existing function to
> something like svm_nested_switch_to_vmcb02()?
> 
> Alternatively, I could go back to introducing a new PMU_OP, call it
> from {enter,leave}_guest_mode(), and drop the wrappers.

We could just call amd_pmu_refresh_host_guest_eventsel_hw() every time we call enter_guest_mode() and leave_guest_mode(), which is more error-prone but there's already other things in that category.

We could also call it from svm_switch_vmcb(), which will add some calls to extra places but I assume that would be fine?

I personally prefer the former tbh, as it's otherwise easy to miss.

> 
> > 
> > [1] https://lore.kernel.org/kvm/20260115011312.3675857-9-yosry.ahmed@linux.dev/
> >
>
Re: [PATCH v2 3/5] KVM: x86/pmu: Refresh Host-Only/Guest-Only eventsel at nested transitions
Posted by Jim Mattson 4 days, 23 hours ago 
On Fri, Jan 30, 2026 at 3:41 PM Yosry Ahmed <yosry.ahmed@linux.dev> wrote:
>
> January 30, 2026 at 3:30 PM, "Jim Mattson" <jmattson@google.com> wrote:
>
>
> >
> > On Fri, Jan 30, 2026 at 7:26 AM Yosry Ahmed <yosry.ahmed@linux.dev> wrote:
> >
> > >
> > > On Thu, Jan 29, 2026 at 03:28:08PM -0800, Jim Mattson wrote:
> > >  Add amd_pmu_refresh_host_guest_eventsel_hw() to recalculate eventsel_hw for
> > >  all PMCs based on the current vCPU state. This is needed because Host-Only
> > >  and Guest-Only counters must be enabled/disabled at:
> > >
> > >  - SVME changes: When EFER.SVME is modified, counters with Guest-Only bits
> > >  need their hardware enable state updated.
> > >
> > >  - Nested transitions: When entering or leaving guest mode, Host-Only
> > >  counters should be disabled/enabled and Guest-Only counters should be
> > >  enabled/disabled accordingly.
> > >
> > >  Introduce svm_enter_guest_mode() and svm_leave_guest_mode() wrappers that
> > >  call enter_guest_mode()/leave_guest_mode() followed by the PMU refresh,
> > >  ensuring the PMU state stays synchronized with guest mode transitions.
> > >
> > >  Signed-off-by: Jim Mattson <jmattson@google.com>
> > >  ---
> > >  arch/x86/kvm/svm/nested.c | 6 +++---
> > >  arch/x86/kvm/svm/pmu.c | 12 ++++++++++++
> > >  arch/x86/kvm/svm/svm.c | 2 ++
> > >  arch/x86/kvm/svm/svm.h | 17 +++++++++++++++++
> > >  4 files changed, 34 insertions(+), 3 deletions(-)
> > >
> > >  diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
> > >  index de90b104a0dd..a7d1901f256b 100644
> > >  --- a/arch/x86/kvm/svm/nested.c
> > >  +++ b/arch/x86/kvm/svm/nested.c
> > >  @@ -757,7 +757,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
> > >  nested_svm_transition_tlb_flush(vcpu);
> > >
> > >  /* Enter Guest-Mode */
> > >  - enter_guest_mode(vcpu);
> > >  + svm_enter_guest_mode(vcpu);
> > >
> > >  FWIW, I think this name is a bit confusing because we also have
> > >  enter_svm_guest_mode(). So we end up with:
> > >
> > >  enter_svm_guest_mode() -> nested_vmcb02_prepare_control() ->
> > >  svm_enter_guest_mode() -> enter_guest_mode()
> > >
> > >  I actually have another proposed change [1] that moves
> > >  enter_guest_mode() directly into enter_svm_guest_mode(), so the sequence
> > >  would end up being:
> > >
> > >  enter_svm_guest_mode() -> svm_enter_guest_mode() -> enter_guest_mode()
> > >
> > Yes, that is confusing. What if I renamed the existing function to
> > something like svm_nested_switch_to_vmcb02()?
> >
> > Alternatively, I could go back to introducing a new PMU_OP, call it
> > from {enter,leave}_guest_mode(), and drop the wrappers.
>
> We could just call amd_pmu_refresh_host_guest_eventsel_hw() every time we call enter_guest_mode() and leave_guest_mode(), which is more error-prone but there's already other things in that category.
>
> We could also call it from svm_switch_vmcb(), which will add some calls to extra places but I assume that would be fine?
>
> I personally prefer the former tbh, as it's otherwise easy to miss.

I'm not a fan of replicating code sequences. Maybe instead of a new
PMU_OP, I could introduce a new KVM_X86_OP, which would be
conceptually more general, even though the current usage would be the
same.

> >
> > >
> > > [1] https://lore.kernel.org/kvm/20260115011312.3675857-9-yosry.ahmed@linux.dev/
> > >
> >

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.